Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to integration or incorporation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to integration and embedding in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uku
    -0.79
    trak
    -0.77
    rimp
    -0.75
    apest
    -0.72
    STAR
    -0.71
    ircraft
    -0.70
    riz
    -0.68
    trap
    -0.67
    UP
    -0.64
    awn
    -0.63
    POSITIVE LOGITS
     academia
    0.89
     society
    0.79
     somew
    0.76
     adulthood
    0.74
     civilisation
    0.72
     layers
    0.71
     humanity
    0.70
     adolescence
    0.68
     realms
    0.67
    theme
    0.66
    Act Density 0.317%

    No Known Activations